From 208c46d48b5e6bb835a1266e94c4e96b8efcae95 Mon Sep 17 00:00:00 2001
From: tharwood3 <tharwood@lbl.gov>
Date: Wed, 29 May 2024 13:53:50 -0700
Subject: [PATCH] feat: functional workflow

---
 .gitignore     |  8 +++++++-
 nf_workflow.nf | 42 +++++++++++++++++++++++++++++-------------
 2 files changed, 36 insertions(+), 14 deletions(-)

diff --git a/.gitignore b/.gitignore
index ebc3ff2..e07fc8e 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,9 @@
 *.ipynb_checkpoints*
 *.env
-*credentials
\ No newline at end of file
+*credentials
+*.log*
+
+# nextflow output dirs
+*.nextflow/
+*nf_output/
+*work/
\ No newline at end of file
diff --git a/nf_workflow.nf b/nf_workflow.nf
index 3ca33c2..94ce526 100644
--- a/nf_workflow.nf
+++ b/nf_workflow.nf
@@ -1,31 +1,47 @@
 #!/usr/bin/env nextflow
 nextflow.enable.dsl=2
 
-params.input_spectra = "README.md"
+// Parameters
+params.inputfiles1 = "/home/tharwood/repos/test_data/files1/"
+params.inputfiles2 = "/home/tharwood/repos/test_data/files2/"
 
-TOOL_FOLDER = "$baseDir/bin"
+params.inputfiles1_name = "supern-WAVE-NatCom-NLDM-Day0"
+params.inputfiles2_name = "supern-WAVE-NatCom-NLDM-Day7"
 
-process processDataPython {
-    publishDir "./nf_output", mode: 'copy'
+params.exp_name = "wavestab1"
 
-    conda "$TOOL_FOLDER/conda_env.yml"
+params.publishdir = "$baseDir"
+TOOL_FOLDER = "$baseDir/bin/carbon_network/carbon_network/use"
+
+process analyzeDataWithNetwork {
+    publishDir "$params.publishdir/nf_output/results", mode: 'copy'
+
+    conda "$TOOL_FOLDER/environment_analysis.yml"
 
     input:
-    file input 
+    path params.inputfiles1
+    path params.inputfiles2
 
     output:
-    file 'python_output.tsv'
+    path "all_ms1_data.csv"
+    path "all_ms2_data.csv"
+    path "OUTPUT_${params.exp_name}_${params.inputfiles1_name}-vs-${params.inputfiles2_name}.csv"
+    path "AnnotatedCarbonNetwork.graphml"
 
     """
-    python $TOOL_FOLDER/python_script.py $input python_output.tsv
+    files1=\$(find $params.inputfiles1 ~+ -type f -name '*.mzML')
+    files2=\$(find $params.inputfiles2 ~+ -type f -name '*.mzML')
+
+    python $TOOL_FOLDER/analyze_metatlas_data_cli.py \
+    --files_group1 \${files1} \
+    --files_group2 \${files2} \
+    --files_group1_name $params.inputfiles1_name \
+    --files_group2_name $params.inputfiles2_name \
+    --exp_name $params.exp_name \
     """
 }
 
 
 workflow {
-    data_ch = Channel.fromPath(params.input_spectra)
-    
-    // Outputting Python
-    processDataPython(data_ch)
-
+    analyzeDataWithNetwork(params.inputfiles1, params.inputfiles2)
 }